SpectraNet delivers stable autoregressive PDE rollouts with lower error and 2.3x fewer parameters than FNO by embedding spectral convolutions in a U-Net and training a residual-target block under semigroup-consistency loss.
International Conference on Learning Representations (ICLR) , year =
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 9verdicts
UNVERDICTED 9roles
background 1polarities
background 1representative citing papers
VAnim creates open-domain text-to-SVG animations via sparse state updates on a persistent DOM tree, identification-first planning, and rendering-aware RL with a new 134k-example benchmark.
CNeVA combines variational behavior latents with rectified-flow generators and soft eligibility to deliver controllable yet realistic traffic simulation on Waymo data.
TAG-DLM integrates graph message passing into masked diffusion language models via topology attention masks on linearized neighborhoods, enabling prompt-based adaptation for node classification, link prediction, and transfer on text-attributed graphs.
A 149M-parameter distributional energy-based verifier with low-rank adapter ensemble reduces constraint violations in structured LLM reasoning and outperforms or matches much larger models on five benchmarks.
Introduces RevCI benchmark and IMPACT multi-agent framework for evidence-level contradiction detection and graded intensity scoring in peer reviews, distilled into efficient TIDE model.
Future-rhyme information is linearly decodable at line boundaries across model families and strengthens with scale, yet only Gemma-3-27B causally depends on it, with the driver migrating to the boundary around layer 30 and localizing to five attention heads.
Transformers show a sharp, task-specific critical window for weight decay application that determines reasoning versus memorization, with middle placement optimal and boundaries as narrow as 100 steps.
TSA adds end-to-end differentiable per-token halting gates to transformers, enabling learned adaptive depth that saves 14-23% token-layer operations with under 0.5% quality loss on language modeling.
citing papers explorer
-
Bridging Spectral Operator Learning and U-Net Hierarchies: SpectraNet for Stable Autoregressive PDE Surrogates
SpectraNet delivers stable autoregressive PDE rollouts with lower error and 2.3x fewer parameters than FNO by embedding spectral convolutions in a U-Net and training a residual-target block under semigroup-consistency loss.
-
VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animation
VAnim creates open-domain text-to-SVG animations via sparse state updates on a persistent DOM tree, identification-first planning, and rendering-aware RL with a new 134k-example benchmark.
-
Controllable Sim Agents with Behavior Latents
CNeVA combines variational behavior latents with rectified-flow generators and soft eligibility to deliver controllable yet realistic traffic simulation on Waymo data.
-
TAG-DLM: Diffusion Language Models for Text-Attributed Graph Learning
TAG-DLM integrates graph message passing into masked diffusion language models via topology attention masks on linearized neighborhoods, enabling prompt-based adaptation for node classification, link prediction, and transfer on text-attributed graphs.
-
Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoning
A 149M-parameter distributional energy-based verifier with low-rank adapter ensemble reduces constraint violations in structured LLM reasoning and outperforms or matches much larger models on five benchmarks.
-
When Reviews Disagree: Fine-Grained Contradiction Analysis in Scientific Peer Reviews
Introduces RevCI benchmark and IMPACT multi-agent framework for evidence-level contradiction detection and graded intensity scoring in peer reviews, distilled into efficient TIDE model.
-
Where's the Plan? Locating Latent Planning in Language Models with Lightweight Mechanistic Interventions
Future-rhyme information is linearly decodable at line boundaries across model families and strengthens with scale, yet only Gemma-3-27B causally depends on it, with the driver migrating to the boundary around layer 30 and localizing to five attention heads.
-
Critical Windows of Complexity Control: When Transformers Decide to Reason or Memorize
Transformers show a sharp, task-specific critical window for weight decay application that determines reasoning versus memorization, with middle placement optimal and boundaries as narrow as 100 steps.
-
Adaptive Computation Depth via Learned Token Routing in Transformers
TSA adds end-to-end differentiable per-token halting gates to transformers, enabling learned adaptive depth that saves 14-23% token-layer operations with under 0.5% quality loss on language modeling.